Submission deadline: January 26, 2018
Author notification: February 26, 2018
Camera ready: March 15, 2018
Writing parallel applications is an arduous and non-trivial task, but also mandatory if one wants to explore the potential of modern multicore processors. This task becomes even harder as different computation devices, such as General Purpose Graphic Processing Units (GPGPUs), Many core processors, and Field Programmable Gate Arrays (FPGAs), are employed to build heterogeneous systems. This imposes new challenges to the scientific community: the creation of models and alternatives to ease parallelism exploitation by the average programmer, considering the peculiarities of the different computation devices.
Another important aspect to consider, specially in applications that run on big systems and manipulate big datasets, is the tradeoff between moving data to a remote processing element to increase parallelism and computing things locally to reduce communication and energy costs, while keeping performance levels. Edge, Fog and In-situ computing intend to tackle this issue by adding computing capabilities to network devices (such as NICs, switches and routers), storage devices or even memory. Those “smart” devices would be able to perform part of the computation that would reduce data transmission over the network and data buses. Moreover, current trend related to the Internet-of-Things predict that an increasing number of devices composed by sensors, actuators and processing elements will be spread around the world, while forming a huge network to collect relevant information to a broad range of applications. All the aforementioned aspects make computing systems even more heterogeneous, intensifying the need for novel programming models.
MPP aims at bringing together researchers interested in presenting contributions to the evolution of existing models or in proposing novel ones, considering the trends on processing/accelerator devices in the context of edge/fog/in-situ computing. MPP 2018 will be held in conjunction with The 32nd IEEE International Parallel and Distributed Processing Symposium (IPDPS 2018), in Vancouver, British Columbia, Canada, on May 25, 2018.
Topics of interest include (but are not limited to):
– Novel execution models and languages for parallelism exploitation;
– Languages, compilers and tools;
– Heterogeneous programming models;
– Synchronization Mechanisms, such as Transactional Memories;
– Smart memories;
– Load-balancing, Scheduling and Placement for Edge/Fog/In-situ Computing;
– Novel Parallel Programming Techniques for Edge/Fog/In-situ Computing;
– Novel Parallel Architectures for Edge/Fog/In-situ Computing;
– Resilience and Fault Tolerance for Edge/Fog/In-situ Computing;
– Theoretical Analysis of Parallelism;
– Smart storage;
– Smart Switches and Smart NICs;
– Software defined Networks for Edge/Fog/In-situ Computing;
– Applications for Edge/Fog/In-situ computing;
– Data Stream Processing.
– Leandro A. J. Marzulo – Universidade do Estado do Rio de Janeiro (UERJ), Brazil
– Felipe M. G. França – Universidade Federal do Rio de Janeiro (UFRJ), Brazil
– Cristiana Bentes – Universidade do Estado do Rio de Janeiro (UERJ), Brazil
– Gabriele Mencagli – University of Pisa, Italy